Hand written digits classification and recognition using convolutional neural networks by implementing the techniques of MLP and SVM

---

作者

Shahid Naseem¹

1. University of Education, Township, Lahore, Pakistan

会议/活动

4th International Conference on Computer Science and Allied Technologies 2022, November 2022 (Lahore, Pakistan)

海报摘要

In this research, we are Convoluting Neural Network (CNN) for handwritten digital pattern recognition and data classification. We have also analyzed the perception of the neural networks required for handwritten digit recognition. A CNN can provide a very thrilling revolutionary and crucial role in today’s computer science field. We have also developed a multi-layered perceptron (MLP) and support vector machine (SVM) to support CNN to recognize and classify handwritten digits. Multi-layered perceptron is used as a hidden layer having 15 units for handwritten digits’ recognition. The testing has been controlled from popular obtainable MNIST recognition images. After processing the data in MLP, it is observed that multi-layered CNN has an accuracy of 0.92% and with SVM has 0.96%.

关键词

Convolutional neural network, SVM, Hand written digits, MLP, Perceptron’s artificial neurons, Characteristics and application

研究领域

Computer and Information Science , Medical Imaging

参考文献

1. V. D. Manu Pratap Singh, "Handwritten character recognition using modified gradient descent technique of neural networks and representation of conjugate descent for training patterns," 2009.
2. Y. Li, Y. Fu, H. Li and S. W. Zhang, "The Improved Training Algorithm of Back Propagation Neural Network with Self-adaptive Learning Rate.," in International Conference on Computational Intelligence and Natural Computing., 2009.
3. C. W. DAWSON, "An artificial neural network approach to rainfall-runoff modelling"," Hydrological Sciences Journal., vol. 43, pp. 47-66, 1998.
4. M. F. Abbod, "Application of Artificial Intelligence to the Management of Urological Cancer"," The Journal of Urology., vol. 178, no. 4, pp. 1150-1156, 2007.
5. Y. V. U. Ravi Babu, "Handwritten Digit Recognition Using K-Nearest Neighbour Classifier," in World Congress on Computing and Communication Technologies (WCCCT), 2014.
6. L. H. S. A. Simon Bernard, "Using Random Forests for Handwritten Digit Recognition," in Using Random Forests for HandwrittenDigit Recognition, Curitiba, Brazil., 2007.
7. P. S. N. Tsehay Admassu Assegie, "Handwritten digits recognition with decision tree classification: a machine learning approach," International Journal of Electrical and Computer Engineering (IJECE) , vol. 9, no. . 5, October 2019, p. 4446~4451 , 2019.
8. G. Cybenko, Approximation by superpositions of a sigmoidal function Mathematics of Control, Signals, and Systems, 1989, pp. 303-314.
9. F. Rosenblatt, Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms., Washington DC, 1961.
10. M. F. Abbod, "Application of Artificial Intelligence to the Management of Urological Cancer"," The Journal of Urology., vol. 178, no. 4, pp. 1150-1156, 2007.

基金

暂无数据

补充材料

1. Description of Poster   Download
2. Certificate of conference   Download

附加信息

利益冲突

No competing interests were disclosed.

数据可用性声明

The datasets generated during and / or analyzed during the current study are available from the corresponding author on reasonable request.

知识共享许可协议

Copyright © 2023 Naseem. This is an open access work distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.